International Conference on Computer and Knowledge Engineering

Home / 13th International Conference on Computer and Knowledge Engineering

Density Estimation Helps Adversarial Robustness

Authors :

Afsaneh Hasanebrahimi¹ Bahareh Kaviani Baghbaderani² Reshad Hosseini³ Ahmad Kalhor⁴

1- College of Engineering, Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran 2- College of Engineering, Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran 3- College of Engineering, Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran 4- College of Engineering, Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran

Keywords :

Variational Autoencoder،Adversarial Robustness

Abstract :

Adversarial attacks pose a threat to deep learning models, as they involve subtle disturbances that are imperceptible to human vision. In this paper, a classification network is introduced that also includes a density estimation head modeled using the decoder of a variational autoencoder. Incorporating the loss of the variational autoencoder during the training of the classifier aids in achieving a robust latent variable. The experimental findings show that the suggested model successfully defends against various gradient-based adversarial attacks, including FGSM, R-FGSM, MI-FGSM, and PGD, in both scenarios involving white-box and black-box contexts.